| Semantic3D.net: a new large-scale point cloud classification benchmark T Hackel, N Savinov, L Ladicky, JD Wegner, K Schindler, M Pollefeys arXiv preprint arXiv:1704.03847, 2017 | 831 | 2017 |
| Gemini: A Family of Highly Capable Multimodal Models G Gemini Team https://storage.googleapis.com/deepmind-media/gemini/gemini_1_report.pdf, 2023 | 407* | 2023 |
| Semi-parametric topological memory for navigation N Savinov, A Dosovitskiy, V Koltun ICLR 2018, 2018 | 392 | 2018 |
| Episodic curiosity through reachability N Savinov, A Raichuk, R Marinier, D Vincent, M Pollefeys, T Lillicrap, ... ICLR 2019, 2019 | 313 | 2019 |
| TI-POOLING: transformation-invariant pooling for feature learning in convolutional neural networks D Laptev, N Savinov, JM Buhmann, M Pollefeys CVPR 2016, 2016 | 300 | 2016 |
| Conditional affordance learning for driving in urban environments A Sauer, N Savinov, A Geiger CoRL 2018, 2018 | 211 | 2018 |
| Quad-networks: unsupervised learning to rank for interest point detection N Savinov, A Seki, L Ladicky, T Sattler, M Pollefeys CVPR 2017, 2017 | 197 | 2017 |
| Imitating interactive intelligence J Abramson, A Ahuja, I Barr, A Brussee, F Carnevale, M Cassin, ... arXiv preprint arXiv:2012.05672, 2020 | 72 | 2020 |
| Step-unrolled denoising autoencoders for text generation N Savinov, J Chung, M Binkowski, E Elsen, A Oord ICLR 2022, 2021 | 71 | 2021 |
| Discrete optimization of ray potentials for semantic 3D reconstruction N Savinov, L Ladicky, C Hane, M Pollefeys CVPR 2015, 2015 | 71 | 2015 |
| Semantic 3D reconstruction with continuous regularization and ray potentials using a visibility consistency constraint N Savinov, C Hane, L Ladicky, M Pollefeys CVPR 2016, 2016 | 63 | 2016 |
| Class specific 3D object shape priors using surface normals C Hane, N Savinov, M Pollefeys CVPR 2014, 2014 | 60 | 2014 |
| Continuous diffusion for categorical data S Dieleman, L Sartran, A Roshannai, N Savinov, Y Ganin, PH Richemond, ... arXiv preprint arXiv:2211.15089, 2022 | 54 | 2022 |
| Self-conditioned embedding diffusion for text generation R Strudel, C Tallec, F Altché, Y Du, Y Ganin, A Mensch, W Grathwohl, ... arXiv preprint arXiv:2211.04236, 2022 | 40* | 2022 |
| Large-scale supervised learning for 3D point cloud labeling: Semantic3d.net T Hackel, JD Wegner, N Savinov, L Ladicky, K Schindler, M Pollefeys Photogrammetric Engineering & Remote Sensing, 2018 | 19 | 2018 |
| Matching neural paths: transfer from recognition to correspondence search N Savinov, L Ladicky, M Pollefeys NeurIPS 2017, 2017 | 12 | 2017 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context M Reid, N Savinov, D Teplyashin, D Lepikhin, T Lillicrap, J Alayrac, ... arXiv preprint arXiv:2403.05530, 2024 | 4 | 2024 |
| RNN-based generative model for fine-grained sketching A Jenal, N Savinov, T Sattler, G Chaurasia arXiv preprint arXiv:1901.03991, 2019 | 4 | 2019 |
| DISCRETE TOKEN PROCESSING USING DIFFUSION MODELS R Strudel, R Leblond, L Sifre, SEL Dieleman, N Savinov, WS Grathwohl, ... US Patent App. 18/374,447, 2024 | | 2024 |
| AlphaCode 2 Technical Report G AlphaCode Team https://storage.googleapis.com/deepmind-media/AlphaCode2 …, 2023 | | 2023 |
Marc PollefeysProfessor of Computer Science, ETH Zurich, and Director Mixed Reality and AI Lab Zurich, MicrosoftVerified email at inf.ethz.ch
